Messages in this thread |  | | | Subject | Re: [PATCH 8/8] vm: Add an tuning knob for vm.max_writeback_mb | | From | Richard Kennedy <> | | Date | Sat, 05 Sep 2009 17:18:16 +0100 |
| |
On Sat, 2009-09-05 at 14:26 +0100, Jamie Lokier wrote: > Richard Kennedy wrote: > > I've been testing this & it works pretty well here, but setting > > max_writeback_mb to 128 seems much too large for normal desktop machines. > > > > Because it is so large the background writes don't stop when they get > > down to the background threshold, but just keep on writing. > > background_threshold on my machine is only about 300Mb so it can > > undershoot by quite a bit. This could impact random write workloads > > significantly. > > If that's true, would it be even worse for embedded devices with, say, > just 32MB RAM? It sounds like writeback undershoot might be rather > extreme in that case.
Well, on a machine that small I don't think it will be any worse. The current code tries to write 1024 pages so its undershoot will be about 100% anyway.
> Also on this topic, should max_writeback be smaller for slow disks? I > have a small device here with a hard disk that can only be written at > 2-10MB/s due to limitations of the built-in IDE controller. > > I know that's unusual, but it shows there is quite a wide range of > speeds at which disks can be written, even just counting hard disks. > > -- Jamie
I'm not sure about that, it will depend on how the background threshold issue gets fixed.
regards Richard
|  |